6 citations · 6 across the 8 of their papers we have counts for
6 papers · 1 filter
When Cosine Similarity Fails to Reflect Linearly Accessible Structure in Dialogue Models
Yu Sun, Mengyin Lu, Cong Feng +2
Cosine similarity is widely used to analyze transformer representations, implicitly assuming that similarity reflects task-relevant structure. We study when this assumption fails i…
K/V-Cache Interventions Dissociate Representation Alignment from Persona Expression in Decoder-Only Language Models
Yu Sun, Mengyin Lu, Cong Feng +2
We study K/V-cache interventions -- transplanting a target-conditioned K/V trajectory into a source-persona generation -- as a structured surface for persona control in decoder-onl…
SPEAR: Code-Augmented Agentic Prompt Optimization
Mengyin Lu, Cong Feng, Huimin Han +6
Automatic prompt engineering (APE) rewrites prompts to improve downstream task performance, but existing APE loops treat the optimizer itself as a fixed pipeline. We port the code-…
BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models
Gaurav Srivastava, Aafiya Hussain, Zhenyu Bi +5
Evaluating language models fairly is increasingly difficult as static benchmarks risk contamination by training data, obscuring whether models truly reason or recall. We introduce…
DEBATE, TRAIN, EVOLVE: Self Evolution of Language Model Reasoning
Gaurav Srivastava, Zhenyu Bi, Meng Lu +1
Large language models (LLMs) have improved significantly in their reasoning through extensive training on massive datasets. However, relying solely on additional data for improveme…
AI for Biomedicine in the Era of Large Language Models
Zhenyu Bi, Sajib Acharjee Dip, Daniel Hajialigol +4
The capabilities of AI for biomedicine span a wide spectrum, from the atomic level, where it solves partial differential equations for quantum systems, to the molecular level, pred…